---
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: my_awesome_model_2
  results: []
---

<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->

# my_awesome_model_2

This model is a fine-tuned version of [distilbert-base-uncased-finetuned-sst-2-english](https://huggingface.co/distilbert-base-uncased-finetuned-sst-2-english) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0950
- Accuracy: 0.9655

## Model description

More information needed

## Intended uses & limitations

More information needed

## Training and evaluation data

More information needed

## Training procedure

### Training hyperparameters

The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| No log        | 0.09  | 200  | 0.4448          | 0.8383   |
| No log        | 0.19  | 400  | 0.2267          | 0.9250   |
| 0.2842        | 0.28  | 600  | 0.1300          | 0.9532   |
| 0.2842        | 0.38  | 800  | 0.1689          | 0.9437   |
| 0.1348        | 0.47  | 1000 | 0.1445          | 0.9530   |
| 0.1348        | 0.57  | 1200 | 0.1237          | 0.9554   |
| 0.1348        | 0.66  | 1400 | 0.1103          | 0.9624   |
| 0.1198        | 0.75  | 1600 | 0.0950          | 0.9655   |
| 0.1198        | 0.85  | 1800 | 0.1115          | 0.9642   |
| 0.1053        | 0.94  | 2000 | 0.1192          | 0.9603   |
| 0.1053        | 1.04  | 2200 | 0.1102          | 0.9622   |
| 0.1053        | 1.13  | 2400 | 0.1096          | 0.9650   |
| 0.0716        | 1.22  | 2600 | 0.1212          | 0.9650   |


### Framework versions

- Transformers 4.26.1
- Pytorch 1.13.1+cu116
- Datasets 2.10.1
- Tokenizers 0.13.2